Web UI for AI browser agent
Top 3.5% on sourcepulse
This project provides a user-friendly Gradio-based web UI for interacting with AI agents that control web browsers. It targets developers and researchers needing to automate web tasks, offering expanded LLM support and flexible browser session management for seamless AI-driven web navigation.
How It Works
The web UI leverages the browser-use
library to enable AI agents to interact with websites. It utilizes Playwright for browser automation, supporting custom browser configurations and persistent sessions. This approach allows AI agents to maintain context across tasks and provides users with visibility into the agent's actions through an integrated VNC viewer.
Quick Start & Requirements
git clone https://github.com/browser-use/web-ui.git && cd web-ui
uv venv --python 3.11
, then activate.uv pip install -r requirements.txt
playwright install --with-deps chromium
.env.example
to .env
and add API keys.python webui.py --ip 127.0.0.1 --port 7788
.env
file as above.docker compose up --build
(default) or CHROME_PERSISTENT_SESSION=true docker compose up --build
(persistent session).http://localhost:7788
, VNC Viewer at http://localhost:6080/vnc.html
.Highlighted Details
CHROME_PATH
and CHROME_USER_DATA
environment variables.Maintenance & Community
Recent updates include integration with DeepSeek-r1 and Docker setup improvements. Community links are not explicitly provided in the README.
Licensing & Compatibility
The license is not specified in the README.
Limitations & Caveats
The README does not specify the project's license, which is crucial for determining commercial use compatibility. It relies on Playwright for browser automation, which may have its own platform-specific limitations.
2 months ago
1 day